© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118610
    Prev
    Next
    INDEX
    Explanations

    expressions that convey negation or the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LOBAL
    -0.07
    lemen
    -0.07
    èĪĹ
    -0.07
    lsruhe
    -0.07
    rador
    -0.07
    dv
    -0.07
    ouse
    -0.07
    شتÙĩ
    -0.06
    ases
    -0.06
    viso
    -0.06
    POSITIVE LOGITS
     except
    0.07
    ania
    0.06
     Gates
    0.06
     more
    0.06
     importance
    0.06
    ença
    0.06
     lead
    0.06
    -e
    0.06
    Lead
    0.06
    ActionCreators
    0.06
    Activations Density 0.022%

    No Known Activations